Technical note: Data assimilation and autoregression for using near-real-time streamflow observations in long short-term memory networks
Grey Nearing, Daniel Klotz, Jonathan Frame, Martin Gauch, Oren Gilon, Frederik Kratzert, Alden Keefe Sampson, Guy Shalev, Sella Nevo
Abstract
Abstract. Ingesting near-real-time observation data is a critical component of many operational hydrological forecasting systems. In this paper, we compare two strategies for ingesting near-real-time streamflow observations into long short-term memory (LSTM) rainfall–runoff models: autoregression (a forward method) and variational data assimilation. Autoregression is both more accurate and more computationally efficient than data assimilation. Autoregression is sensitive to missing data, however an appropriate (and simple) training strategy mitigates this problem. We introduce a data assimilation procedure for recurrent deep learning models that uses backpropagation to make the state updates.